[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/parserHelperTests AllTests.java,1.24,1.25 Compo
Brought to you by:
derrickoswald
Menu
▾
▴
[Htmlparser-cvs] htmlparser/src/org/htmlparser/tests/parserHelperTests AllTests.java,1.24,1.25 CompositeTagScannerHelperTest.java,1.17,1.18 StringParserTest.java,1.34,1.35
|
From: <der...@us...> - 2003-09-03 23:36:24
|
Update of /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests
In directory sc8-pr-cvs1:/tmp/cvs-serv31228/tests/parserHelperTests
Modified Files:
AllTests.java CompositeTagScannerHelperTest.java
StringParserTest.java
Log Message:
Change tabs to spaces in all source files.
Index: AllTests.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/AllTests.java,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** AllTests.java 24 Aug 2003 21:59:43 -0000 1.24
--- AllTests.java 3 Sep 2003 23:36:21 -0000 1.25
***************
*** 39,48 ****
public static TestSuite suite() {
TestSuite suite = new TestSuite("Parser Helper Tests");
! // To-do: Test below should be enabled after it passes
// suite.addTestSuite(AttributeParserTest.class);
suite.addTestSuite(CompositeTagScannerHelperTest.class);
suite.addTestSuite(RemarkNodeParserTest.class);
suite.addTestSuite(StringParserTest.class);
! // To-do: Test below should be enabled after it passes
// suite.addTestSuite(TagParserTest.class);
--- 39,48 ----
public static TestSuite suite() {
TestSuite suite = new TestSuite("Parser Helper Tests");
! // To-do: Test below should be enabled after it passes
// suite.addTestSuite(AttributeParserTest.class);
suite.addTestSuite(CompositeTagScannerHelperTest.class);
suite.addTestSuite(RemarkNodeParserTest.class);
suite.addTestSuite(StringParserTest.class);
! // To-do: Test below should be enabled after it passes
// suite.addTestSuite(TagParserTest.class);
Index: CompositeTagScannerHelperTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/CompositeTagScannerHelperTest.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** CompositeTagScannerHelperTest.java 24 Aug 2003 21:59:43 -0000 1.17
--- CompositeTagScannerHelperTest.java 3 Sep 2003 23:36:21 -0000 1.18
***************
*** 41,70 ****
*/
public class CompositeTagScannerHelperTest extends ParserTestCase {
! private CompositeTagScannerHelper helper;
! public CompositeTagScannerHelperTest(String name) {
! super(name);
! }
! protected void setUp() {
! helper =
! new CompositeTagScannerHelper(null,null,null,null,null,false);
! }
!
! public void testIsXmlEndTagForRealXml() {
! Tag tag = new Tag(
! new TagData(
! 0,0,"something/",""
! )
! );
! assertTrue("should be an xml end tag",helper.isXmlEndTag(tag));
! }
! public void testIsXmlEndTagForFalseMatches() {
! Tag tag = new Tag(
! new TagData(
! 0,0,"a href=http://someurl.com/",""
! )
! );
! assertFalse("should not be an xml end tag",helper.isXmlEndTag(tag));
! }
}
--- 41,70 ----
*/
public class CompositeTagScannerHelperTest extends ParserTestCase {
! private CompositeTagScannerHelper helper;
! public CompositeTagScannerHelperTest(String name) {
! super(name);
! }
! protected void setUp() {
! helper =
! new CompositeTagScannerHelper(null,null,null,null,null,false);
! }
!
! public void testIsXmlEndTagForRealXml() {
! Tag tag = new Tag(
! new TagData(
! 0,0,"something/",""
! )
! );
! assertTrue("should be an xml end tag",helper.isXmlEndTag(tag));
! }
! public void testIsXmlEndTagForFalseMatches() {
! Tag tag = new Tag(
! new TagData(
! 0,0,"a href=http://someurl.com/",""
! )
! );
! assertFalse("should not be an xml end tag",helper.isXmlEndTag(tag));
! }
}
Index: StringParserTest.java
===================================================================
RCS file: /cvsroot/htmlparser/htmlparser/src/org/htmlparser/tests/parserHelperTests/StringParserTest.java,v
retrieving revision 1.34
retrieving revision 1.35
diff -C2 -d -r1.34 -r1.35
*** StringParserTest.java 24 Aug 2003 21:59:43 -0000 1.34
--- StringParserTest.java 3 Sep 2003 23:36:21 -0000 1.35
***************
*** 40,209 ****
public class StringParserTest extends ParserTestCase {
! public StringParserTest(String name) {
! super(name);
! }
!
! /**
! * The bug being reproduced is this : <BR>
! * <HTML><HEAD><TITLE>Google</TITLE> <BR>
! * The above line is incorrectly parsed in that, the text Google is missed.
! * The presence of this bug is typically when some tag is identified before the string node is. (usually seen
! * with the end tag). The bug lies in NodeReader.readElement().
! * Creation date: (6/17/2001 4:01:06 PM)
! */
! public void testStringNodeBug1() throws ParserException {
! createParser("<HTML><HEAD><TITLE>Google</TITLE>");
! parseAndAssertNodeCount(5);
! // The fourth node should be a HTMLStringNode- with the text - Google
! assertTrue("Fourth node should be a HTMLStringNode",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("Text of the StringNode","Google",stringNode.getText());
! }
!
! /**
! * Bug reported by Kaarle Kaila of Nokia<br>
! * For the following HTML :
! * view these documents, you must have <A href='http://www.adobe.com'>Adobe <br>
! * Acrobat Reader</A> installed on your computer.<br>
! * The first string before the link is not identified, and the space after the link is also not identified
! * Creation date: (8/2/2001 2:07:32 AM)
! */
! public void testStringNodeBug2() throws ParserException {
! // Register the link scanner
!
! createParser("view these documents, you must have <A href='http://www.adobe.com'>Adobe \n"+
! "Acrobat Reader</A> installed on your computer.");
! Parser.setLineSeparator("\r\n");
! parser.addScanner(new LinkScanner("-l"));
! parseAndAssertNodeCount(3);
! // The first node should be a HTMLStringNode- with the text - view these documents, you must have
! assertTrue("First node should be a HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("Text of the StringNode","view these documents, you must have ",stringNode.getText());
! assertTrue("Second node should be a link node",node[1] instanceof LinkTag);
! LinkTag linkNode = (LinkTag)node[1];
! assertEquals("Link is","http://www.adobe.com",linkNode.getLink());
! assertEquals("Link text is","Adobe \r\nAcrobat Reader",linkNode.getLinkText());
!
! assertTrue("Third node should be a string node",node[2] instanceof StringNode);
! StringNode stringNode2 = (StringNode)node[2];
! assertEquals("Contents of third node"," installed on your computer.",stringNode2.getText());
! }
!
! /**
! * Bug reported by Roger Sollberger<br>
! * For the following HTML :
! * <a href="http://asgard.ch">[< ASGARD ></a><br>
! * The string node is not correctly identified
! */
! public void testTagCharsInStringNode() throws ParserException {
! createParser("<a href=\"http://asgard.ch\">[> ASGARD <]</a>");
! parser.addScanner(new LinkScanner("-l"));
! parseAndAssertNodeCount(1);
! assertTrue("Node identified must be a link tag",node[0] instanceof LinkTag);
! LinkTag linkTag = (LinkTag) node[0];
! assertEquals("[> ASGARD <]",linkTag.getLinkText());
! assertEquals("http://asgard.ch",linkTag.getLink());
! }
!
! public void testToPlainTextString() throws ParserException {
! createParser("<HTML><HEAD><TITLE>This is the Title</TITLE></HEAD><BODY>Hello World, this is the HTML Parser</BODY></HTML>");
! parseAndAssertNodeCount(10);
! assertTrue("Fourth Node identified must be a string node",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("First String Node","This is the Title",stringNode.toPlainTextString());
! assertTrue("Eighth Node identified must be a string node",node[7] instanceof StringNode);
! stringNode = (StringNode)node[7];
! assertEquals("Second string node","Hello World, this is the HTML Parser",stringNode.toPlainTextString());
! }
!
! public void testToHTML() throws ParserException {
! createParser("<HTML><HEAD><TITLE>This is the Title</TITLE></HEAD><BODY>Hello World, this is the HTML Parser</BODY></HTML>");
! parseAndAssertNodeCount(10);
! assertTrue("Fourth Node identified must be a string node",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("First String Node","This is the Title",stringNode.toHtml());
! assertTrue("Eighth Node identified must be a string node",node[7] instanceof StringNode);
! stringNode = (StringNode)node[7];
! assertEquals("Second string node","Hello World, this is the HTML Parser",stringNode.toHtml());
! }
! public void testEmptyLines() throws ParserException {
! createParser(
! "David Nirenberg (Center for Advanced Study in the Behavorial Sciences, Stanford).<br>\n"+
! " \n"+
! "<br>"
! );
! parseAndAssertNodeCount(4);
! assertTrue("Third Node identified must be a string node",node[2] instanceof StringNode);
! }
! /**
! * This is a bug reported by John Zook (586222), where the first few chars
! * before a remark is being missed, if its on the same line.
! */
! public void testStringBeingMissedBug() throws ParserException {
! createParser(
! "Before Comment <!-- Comment --> After Comment"
! );
! parseAndAssertNodeCount(3);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! assertTrue("Second node should be HTMLRemarkNode",node[1] instanceof RemarkNode);
! assertTrue("Third node should be HTMLStringNode",node[2] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("First String node contents","Before Comment ",stringNode.getText());
! StringNode stringNode2 = (StringNode)node[2];
! assertEquals("Second String node contents"," After Comment",stringNode2.getText());
! RemarkNode remarkNode = (RemarkNode)node[1];
! assertEquals("Remark Node contents"," Comment ",remarkNode.getText());
!
! }
! /**
! * Based on a bug report submitted by Cedric Rosa, if the last line contains a single character,
! * StringNode does not return the string node correctly.
! */
! public void testLastLineWithOneChar() throws ParserException {
! createParser("a");
! parseAndAssertNodeCount(1);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("First String node contents","a",stringNode.getText());
! }
!
! public void testStringWithEmptyLine() throws ParserException {
! createParser("a\n\nb");
! parseAndAssertNodeCount(1);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertStringEquals("First String node contents","a\r\n\r\nb",stringNode.getText());
! }
!
! /**
! * An attempt to reproduce bug 677176, which passes.
! * @throws Exception
! */
! public void testStringParserBug() throws Exception {
! createParser(
! "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 " +
"Transitional//EN\">" +
"<html>" +
"<head>" +
"<title>Untitled Document</title>" +
"<meta http-equiv=\"Content-Type\" content=\"text/html; " +
"charset=iso-8859-1\">" +
"</head>" +
"<script language=\"JavaScript\" type=\"text/JavaScript\">" +
"// if this fails, output a 'hello' " +
"if (true) " +
"{ " +
"//something good... " +
"} " +
"</script>" +
"<body>" +
"</body>" +
"</html>"
);
! parser.registerScanners();
! parseAndAssertNodeCount(10);
! assertType("fourth node",MetaTag.class,node[4]);
! MetaTag metaTag = (MetaTag)node[4];
!
! assertStringEquals(
! "content",
! "text/html; charset=iso-8859-1",
! metaTag.getAttribute("CONTENT")
! );
! }
!
! public void testStringWithLineBreaks() throws Exception {
! createParser("Testing &\nRefactoring");
! parseAndAssertNodeCount(1);
! assertType("first node",StringNode.class,node[0]);
! StringNode stringNode = (StringNode)node[0];
! assertStringEquals("text","Testing &\r\nRefactoring",stringNode.toPlainTextString());
! }
!
}
--- 40,227 ----
public class StringParserTest extends ParserTestCase {
! public StringParserTest(String name) {
! super(name);
! }
!
! /**
! * The bug being reproduced is this : <BR>
! * <HTML><HEAD><TITLE>Google</TITLE> <BR>
! * The above line is incorrectly parsed in that, the text Google is missed.
! * The presence of this bug is typically when some tag is identified before the string node is. (usually seen
! * with the end tag). The bug lies in NodeReader.readElement().
! * Creation date: (6/17/2001 4:01:06 PM)
! */
! public void testStringNodeBug1() throws ParserException {
! createParser("<HTML><HEAD><TITLE>Google</TITLE>");
! parseAndAssertNodeCount(5);
! // The fourth node should be a HTMLStringNode- with the text - Google
! assertTrue("Fourth node should be a HTMLStringNode",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("Text of the StringNode","Google",stringNode.getText());
! }
!
! /**
! * Bug reported by Kaarle Kaila of Nokia<br>
! * For the following HTML :
! * view these documents, you must have <A href='http://www.adobe.com'>Adobe <br>
! * Acrobat Reader</A> installed on your computer.<br>
! * The first string before the link is not identified, and the space after the link is also not identified
! * Creation date: (8/2/2001 2:07:32 AM)
! */
! public void testStringNodeBug2() throws ParserException {
! // Register the link scanner
!
! createParser("view these documents, you must have <A href='http://www.adobe.com'>Adobe \n"+
! "Acrobat Reader</A> installed on your computer.");
! Parser.setLineSeparator("\r\n");
! parser.addScanner(new LinkScanner("-l"));
! parseAndAssertNodeCount(3);
! // The first node should be a HTMLStringNode- with the text - view these documents, you must have
! assertTrue("First node should be a HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("Text of the StringNode","view these documents, you must have ",stringNode.getText());
! assertTrue("Second node should be a link node",node[1] instanceof LinkTag);
! LinkTag linkNode = (LinkTag)node[1];
! assertEquals("Link is","http://www.adobe.com",linkNode.getLink());
! assertEquals("Link text is","Adobe \r\nAcrobat Reader",linkNode.getLinkText());
!
! assertTrue("Third node should be a string node",node[2] instanceof StringNode);
! StringNode stringNode2 = (StringNode)node[2];
! assertEquals("Contents of third node"," installed on your computer.",stringNode2.getText());
! }
!
! /**
! * Bug reported by Roger Sollberger<br>
! * For the following HTML :
! * <a href="http://asgard.ch">[< ASGARD ></a><br>
! * The string node is not correctly identified
! */
! public void testTagCharsInStringNode() throws ParserException {
! createParser("<a href=\"http://asgard.ch\">[> ASGARD <]</a>");
! parser.addScanner(new LinkScanner("-l"));
! parseAndAssertNodeCount(1);
! assertTrue("Node identified must be a link tag",node[0] instanceof LinkTag);
! LinkTag linkTag = (LinkTag) node[0];
! assertEquals("[> ASGARD <]",linkTag.getLinkText());
! assertEquals("http://asgard.ch",linkTag.getLink());
! }
!
! public void testToPlainTextString() throws ParserException {
! createParser("<HTML><HEAD><TITLE>This is the Title</TITLE></HEAD><BODY>Hello World, this is the HTML Parser</BODY></HTML>");
! parseAndAssertNodeCount(10);
! assertTrue("Fourth Node identified must be a string node",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("First String Node","This is the Title",stringNode.toPlainTextString());
! assertTrue("Eighth Node identified must be a string node",node[7] instanceof StringNode);
! stringNode = (StringNode)node[7];
! assertEquals("Second string node","Hello World, this is the HTML Parser",stringNode.toPlainTextString());
! }
!
! public void testToHTML() throws ParserException {
! createParser("<HTML><HEAD><TITLE>This is the Title</TITLE></HEAD><BODY>Hello World, this is the HTML Parser</BODY></HTML>");
! parseAndAssertNodeCount(10);
! assertTrue("Fourth Node identified must be a string node",node[3] instanceof StringNode);
! StringNode stringNode = (StringNode)node[3];
! assertEquals("First String Node","This is the Title",stringNode.toHtml());
! assertTrue("Eighth Node identified must be a string node",node[7] instanceof StringNode);
! stringNode = (StringNode)node[7];
! assertEquals("Second string node","Hello World, this is the HTML Parser",stringNode.toHtml());
! }
! public void testEmptyLines() throws ParserException {
! createParser(
! "David Nirenberg (Center for Advanced Study in the Behavorial Sciences, Stanford).<br>\n"+
! " \n"+
! "<br>"
! );
! parseAndAssertNodeCount(4);
! assertTrue("Third Node identified must be a string node",node[2] instanceof StringNode);
! }
! /**
! * This is a bug reported by John Zook (586222), where the first few chars
! * before a remark is being missed, if its on the same line.
! */
! public void testStringBeingMissedBug() throws ParserException {
! createParser(
! "Before Comment <!-- Comment --> After Comment"
! );
! parseAndAssertNodeCount(3);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! assertTrue("Second node should be HTMLRemarkNode",node[1] instanceof RemarkNode);
! assertTrue("Third node should be HTMLStringNode",node[2] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("First String node contents","Before Comment ",stringNode.getText());
! StringNode stringNode2 = (StringNode)node[2];
! assertEquals("Second String node contents"," After Comment",stringNode2.getText());
! RemarkNode remarkNode = (RemarkNode)node[1];
! assertEquals("Remark Node contents"," Comment ",remarkNode.getText());
!
! }
! /**
! * Based on a bug report submitted by Cedric Rosa, if the last line contains a single character,
! * StringNode does not return the string node correctly.
! */
! public void testLastLineWithOneChar() throws ParserException {
! createParser("a");
! parseAndAssertNodeCount(1);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertEquals("First String node contents","a",stringNode.getText());
! }
!
! public void testStringWithEmptyLine() throws ParserException {
! createParser("a\n\nb");
! parseAndAssertNodeCount(1);
! assertTrue("First node should be HTMLStringNode",node[0] instanceof StringNode);
! StringNode stringNode = (StringNode)node[0];
! assertStringEquals("First String node contents","a\r\n\r\nb",stringNode.getText());
! }
!
! /**
! * An attempt to reproduce bug 677176, which passes.
! * @throws Exception
! */
! public void testStringParserBug() throws Exception {
! createParser(
! "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 " +
! "Transitional//EN\">" +
! "<html>" +
! "<head>" +
! "<title>Untitled Document</title>" +
! "<meta http-equiv=\"Content-Type\" content=\"text/html; " +
! "charset=iso-8859-1\">" +
! "</head>" +
! "<script language=\"JavaScript\" type=\"text/JavaScript\">" +
! "// if this fails, output a 'hello' " +
! "if (true) " +
! "{ " +
! "//something good... " +
! "} " +
! "</script>" +
! "<body>" +
! "</body>" +
! "</html>"
! );
! parser.registerScanners();
! parseAndAssertNodeCount(10);
! assertType("fourth node",MetaTag.class,node[4]);
! MetaTag metaTag = (MetaTag)node[4];
!
! assertStringEquals(
! "content",
! "text/html; charset=iso-8859-1",
! metaTag.getAttribute("CONTENT")
! );
! }
!
! public void testStringWithLineBreaks() throws Exception {
! createParser("Testing &\nRefactoring");
! parseAndAssertNodeCount(1);
! assertType("first node",StringNode.class,node[0]);
! StringNode stringNode = (StringNode)node[0];
! assertStringEquals("text","Testing &\r\nRefactoring",stringNode.toPlainTextString());
! }
!
}
|
